6 papers
TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models
Yang Dai, Oubo Ma, Longfei Zhang +6
Recent advances in Trajectory Optimization (TO) models have achieved remarkable success in offline reinforcement learning. However, their vulnerabilities against backdoor attacks a…
Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
Oubo Ma, Ruixiao Lin, Yang Dai +4
Extensive research has highlighted the severe threats posed by backdoor attacks to deep reinforcement learning (DRL). However, prior studies primarily focus on vanilla scenarios, w…
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
Fanqing Meng, Lingxiao Du, Zijian Wu +46
Language-model agents are increasingly used as persistent coworkers that assist users across multiple working days. During such workflows, the surrounding environment may change in…
Flow-based Policy With Distributional Reinforcement Learning in Trajectory Optimization
Ruijie Hao, Longfei Zhang, Yang Dai +3
Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL algorithms, the policy is typically…
The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers
Wei Tao, Yang Dai, Jincai Huang +1
Crafting adversarial examples can be formulated as an optimization problem. While sign-based optimizers such as I-FGSM and MI-FGSM have become the de facto standard for the induced…
UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning
Oubo Ma, Linkang Du, Yang Dai +4
Deep reinforcement learning (DRL) is widely applied to safety-critical decision-making scenarios. However, DRL is vulnerable to backdoor attacks, especially action-level backdoors,…